Sökning: "segmenteringsmetoder"

Visar resultat 1 - 5 av 7 uppsatser innehållade ordet segmenteringsmetoder.

  1. 1. Online Unsupervised Domain Adaptation

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Theodoros Panagiotakopoulos; [2022]
    Nyckelord :Unsupervised Domain Adaptation; Continual Learning; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantic Segmentation; Transfer Learning; Online Learning; Unsupervised Domain Adaptation; Kontinuerligt lärande; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantisk Segmentering; Transfer Learning; Online Learning;

    Sammanfattning : Deep Learning models have seen great application in demanding tasks such as machine translation and autonomous driving. However, building such models has proved challenging, both from a computational perspective and due to the requirement of a plethora of annotated data. LÄS MER

  3. 2. Pushing the boundary of Semantic Image Segmentation

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Shipra Jain; [2020]
    Nyckelord :Deep Learning; computer vision; semantic segmentation; metric learning; contrastive learning; Djup lärning; datorsyn; semantisk segmentering; metrisk inlärning; kontrastivt lärande;

    Sammanfattning : The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets are fairly limited. This is not surprising , when the restrictions caused by the lack of labeled data and high computation demand are considered. LÄS MER

  4. 3. Text Recognition in Natural Images : A study in Text Detection

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Jan Brifkany; Anass El Yasini; [2020]
    Nyckelord :;

    Sammanfattning : In recent years, a surge in computer vision methods and solutions has been developed to solve the computer vision problem. By combining different methods from different areas of computer vision, computer scientists have been able to develop more advanced and sophisticated models to solve these problems. LÄS MER

  5. 4. Deep Learning models for semantic segmentation of mammography screenings

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Albert Bou; [2019]
    Nyckelord :;

    Sammanfattning : This work explores the performance of state-of-the-art semantic segmentation models on mammographic imagery. It does so by comparing several reference semantic segmentation deep learning models on a newly proposed medical dataset of mammograpgy screenings. LÄS MER

  7. 5. Two-Stage Logistic Regression Models for Improved Credit Scoring

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Anton Lund; [2015]
    Nyckelord :Machine Learning; Credit Scoring; Two-stage Logistic Regressions;

    Sammanfattning : This thesis has investigated two-stage regularized logistic regressions applied on the credit scoring problem. Credit scoring refers to the practice of estimating the probability that a customer will default if given credit. LÄS MER